Vinkius
OpenEI logo
Vinkius
Vinkius runs on Vercel AI SDK

How to Use the OpenEI MCP in Vercel AI SDK

Pipe real-time utility rates directly into your React frontend using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

OpenEI MCP on Cursor AI Code Editor MCP Client OpenEI MCP on Claude Desktop App MCP Integration OpenEI MCP on OpenAI Agents SDK MCP Compatible OpenEI MCP on Visual Studio Code MCP Extension Client OpenEI MCP on GitHub Copilot AI Agent MCP Integration OpenEI MCP on Google Gemini AI MCP Integration OpenEI MCP on Lovable AI Development MCP Client OpenEI MCP on Mistral AI Agents MCP Compatible OpenEI MCP on Amazon AWS Bedrock MCP Support
MCP Servers — Included with Plan
Vinkius runs on Vercel AI SDK

Connect OpenEI MCP to Vercel AI SDK

Create your Vinkius account to connect OpenEI to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Key Capabilities

Render commercial tariffs live in your React UI

The `get_commercial_rates` tool pulls active commercial energy tariffs directly into your Vercel AI SDK frontend stream. Instead of making your users stare at a static loading wheel, you pipe the raw rate structures directly into your UI components as the data arrives from the API. This matters when you are building commercial solar calculators where speed determines whether a user stays on the page. You configure this by calling the `mcpClient.tools()` method and passing the output straight to your text generation engine. The agent identifies the commercial rates, and your application renders the breakdown instantly. There is no middleman and no custom backend polling code to write.

Resolve local rates with this geocoding MCP Server

The `get_rates_by_address` tool matches physical street addresses with their actual utility providers and active tariff schedules. Your UI takes a user's input, routes it through the Vercel AI SDK, and displays the exact residential or commercial rate options without requiring manual zip code lookups. Homeowners get instant feedback on their potential solar savings. This integration runs smoothly on Edge Functions, keeping your API latency low. You just pass the address string, and the system handles the geocoding and tariff lookup in one fast execution step.

Compare complex industrial rate structures in real-time

The `get_industrial_rates` tool retrieves heavy manufacturing tariffs, including complex demand charges and power factor penalties. Industrial energy modeling is notoriously messy, but streaming these rates directly into your Vercel AI SDK application lets you parse the data on the fly. Your users see the cost curves build out in real-time. To drill down further, you can chain the response to `get_rate_detail` for a granular look at seasonal variations. Your client handles the nested JSON data from the MCP Server and formats it into clean UI tables instantly.

Setup guide

Set up OpenEI MCP in Vercel AI SDK

Prerequisites

  • Node.js 18+ and a TypeScript project
  • ai + @modelcontextprotocol/sdk packages
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install dependencies

    Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).

  2. 2

    Create the Streamable HTTP transport

    Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

  3. 3

    Discover and use tools

    Call mcpClient.tools() to auto-discover all OpenEI tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.

  4. 4

    Works with any model provider

    Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts
import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent OpenEI transactions",
});

console.log(text);
await mcpClient.close();

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by OpenEI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about OpenEI MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and configure a client pointing to your Vinkius endpoint. Passing the OpenEI MCP tools directly to `streamText` lets your UI render the tariff structures as they stream in from the server.
Yes, the transport layer uses lightweight HTTP POST requests. This setup allows your edge functions to query rates via `get_rates_by_coordinates` without cold-start penalties.
You should manage API thresholds by caching frequent queries. If a user queries `get_utility_rates` repeatedly, cache the JSON payload in your Next.js data layer to avoid hitting OpenEI limits.
Always call `mcpClient.close()` when your component unmounts or the generation completes. This prevents socket leaks and keeps your serverless environments clean.
Vinkius processes all requests inside an isolated V8 sandbox, meaning your tariff queries and coordinates are never logged. The utility rate data itself is public record, but your users' physical addresses remain completely private and ephemeral.

Start using the OpenEI MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for OpenEI. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.